Identification of an immune-related gene panel for the diagnosis of pulmonary arterial hypertension using bioinformatics and machine learning.

This study aimed to screen an immune-related gene (IRG) panel and develop a novel approach for diagnosing pulmonary arterial hypertension (PAH) utilizing bioinformatics and machine learning (ML). Gene expression profiles were retrieved from the Gene Expression Omnibus (GEO) database to identify differentially expressed immune-related genes (IRG-DEGs). We employed five machine learning algorithms-LASSO, random forest (RF), boosted regression trees (BRT), XGBoost, and support vector machine recursive feature elimination (SVM-RFE) to identify biomarkers derived from IRG-DEGs associated with the diagnosis of PAH, incorporating them into the IRG-DEGs panel. Validation of these biomarker levels in lung tissue was conducted in a hypoxia-induced mouse model of PAH, investigating the correlation between AIMP1, IL-15, GLRX, SOD1, Fulton's index (RVHI), and the ratio of pulmonary artery medial thickness to external diameter (MT%). Subsequently, we developed a nomogram model based on the IRG-DEGs panel in lung tissue for diagnosing PAH. The expression, distribution, and pseudotime analysis of these biomarkers across various immune cell types were assessed using single-cell sequencing datasets. Finally, we evaluated the diagnostic utility of the nomogram model based on the IRG-DEGs panel in peripheral blood mononuclear cells (PBMCs) for diagnosing PAH. A total of 36 upregulated and 17 downregulated IRG-DEGs were identified in lung tissue from patients with PAH. AIMP1, IL-15, GLRX, and SOD1 were subsequently selected as novel immune-related biomarkers for PAH through the aforementioned machine learning algorithms and incorporated into the IRG-DEGs panel. Experimental results from mice with PAH validated that the expression levels of AIMP1, IL-15, and GLRX in lung tissue were elevated, while SOD1 expression was significantly reduced. Additionally, GLRX and AIMP1 exhibited positive correlations with Fulton's index (RVHI). The expression levels of GLRX, IL-15, and AIMP1 showed positive correlations with MT%, whereas SOD1 exhibited negative correlations with MT%. Analysis of single-cell sequencing data further revealed that the levels of IRG-DEG panel members gradually increased during the pseudotime trajectory from PBMCs to macrophages, correlating with macrophage activation. The area under the curve (AUC) for diagnosing PAH using a nomogram model based on the IRG-DEGs panel derived from lung tissue samples and PBMCs was ≥0.969 and 0.900, respectively. We developed an IRG-DEGs panel containing AIMP1, IL-15, GLRX, and SOD1, which may facilitate the diagnosis of pulmonary arterial hypertension (PAH). These findings provide novel insights that may enhance diagnostic and therapeutic approaches for PAH.

Xiong P ，Huang Q ，Mao Y ，Qian H ，Yang Y ，Mou Z ，Deng X ，Wang G ，He B ，You Z ... -  《-》

[Exploration of key ferroptosis-related genes as therapeutic targets for sepsis based on bioinformatics and the depiction of their immune profiles characterization].

Li M ，Mei Y ，Pan A 《-》

Exploring Cuproptosis-Related Genes and Diagnostic Models in Renal Ischemia-Reperfusion Injury Using Bioinformatics, Machine Learning, and Experimental Validation.

Renal ischemia-reperfusion injury (RIRI) is a significant cause of acute kidney injury, complicating clinical interventions such as kidney transplants and partial nephrectomy. Recent research has indicated the role of cuproptosis, a copper-dependent cell death pathway, in various pathologies, but its specific involvement in RIRI remains insufficiently understood. This study aims to investigate the role of cuproptosis-related genes in RIRI and establish robust diagnostic models. We analyzed transcriptomic data from 203 RIRI and 188 control samples using bioinformatics tools to identify cuproptosis-related differentially expressed genes (CRDEGs). The relationship between CRDEGs and immune cells was explored using immune infiltration analysis and correlation analysis. Gene Set Enrichment Analysis (GSEA) was conducted to identify pathways associated with CRDEGs. Machine learning models, including Least Absolute Shrinkage and Selection Operator(LASSO) logistic regression, Support Vector Machine Recursive Feature Elimination (SVM-RFE), Clustering analysis, and weighted gene co-expression network analysis (WGCNA), were used to construct diagnostic gene models. The models were validated using independent datasets. Experimental validation was conducted in vivo using a mouse bilateral RIRI model and in vitro using an HK-2 cell hypoxia-reoxygenation (HR) model with copper chelation intervention. HE, PAS, and TUNEL staining, along with plasma creatinine and blood urea nitrogen (BUN) measurements, were used to evaluate the protective effect of the copper chelator D-Penicillamine (D-PCA) on RIRI in mice. JC-1 and TUNEL staining were employed to assess apoptosis in HK-2 cells under hypoxia-reoxygenation conditions. Immunofluorescence and Western blot (WB) techniques were used to verify the expression levels of the SDHB and NDUFB6 genes. A total of 18 CRDEGs were identified, many of which were significantly correlated with immune cell infiltration. GSEA revealed that these genes were involved in pathways related to oxidative phosphorylation and immune response regulation. Four key cuproptosis marker genes (LIPA, LIPT1, SDHB, and NDUFB6) were incorporated into a Cuproptosis Marker Gene Model(CMGM), achieving an area under the curve (AUC) of 0.741-0.834 in validation datasets. In addition, a five-hub-gene SVM model (MOAP1, PPP2CA, SYL2, ZZZ3, and SFRS2) was developed, demonstrating promising diagnostic performance. Clustering analysis revealed two RIRI subtypes (C1 and C2) with distinct molecular profiles and pathway activities, particularly in oxidative phosphorylation and immune responses. Experimental results showed that copper chelation alleviated renal damage and cuproptosis in both in vivo and in vitro models. Our study reveals that cuproptosis-related genes are significantly involved in RIRI, particularly influencing mitochondrial dysfunction and immune responses. The diagnostic models developed showed promising predictive performance across independent datasets. Copper chelation demonstrated potential therapeutic effects, suggesting that cuproptosis regulation may be a viable therapeutic strategy for RIRI. This work provides a foundation for further exploration of copper metabolism in renal injury contexts.

Xu C ，Deng Y ，Gong X ，Wang H ，Man J ，Wang H ，Cheng K ，Gui H ，Fu S ，Wei S ，Zheng X ，Che T ，Ding L ，Yang L ... -  《Journal of Inflammation Research》

Identification and validation of apoptosis-related genes in acute myocardial infarction based on integrated bioinformatics methods.

Acute myocardial infarction (AMI) is one of the most serious cardiovascular diseases. Apoptosis is a type of programmed cell death that causes DNA degradation and chromatin condensation. The role of apoptosis in AMI progression remains unclear. Three AMI-related microarray datasets (GSE48060, GSE66360 and GSE97320) were obtained from the Gene Expression Omnibus database and combined for further analysis. Differential expression analysis and enrichment analysis were performed on the combined dataset to identify differentially expressed genes (DEGs). Apoptosis-related genes (ARGs) were screened through the intersection of genes associated with apoptosis in previous studies and DEGs. The expression pattern of ARGs was studied on the basis of their raw expression data. Three machine learning algorithms, Least Absolute Shrinkage and Selection Operator (LASSO), support vector machine-recursive feature elimination (SVM-RFE), and Random Forest (RF) were utilized to screen crucial genes in these ARGs. Immune infiltration was estimated by single sample gene set enrichment analysis (ssGSEA). Corresponding online databases were used to predict miRNAs, transcription factors (TFs) and therapeutic agents of crucial genes. A nomogram clinical prediction model of the crucial genes was constructed and evaluated. The Mendelian randomization analysis was employed to investigate whether there is a causal relationship between apoptosis and AMI. Finally, an AMI mouse model was established, and apoptosis in the hearts of AMI mice was assessed via TUNEL staining. qRT-PCR was employed to validate these crucial genes in the hearts of AMI mice. The external dataset GSE59867 was used for further validating the crucial genes. Fifteen ARGs (GADD45A, DDIT3, FEZ1, PMAIP1, IER3, IFNGR1, CDKN1A, GNA15, IL1B, EREG, BCL10, JUN, EGR3, GADD45B, and CD14) were identified. Six crucial genes (CDKN1A, BCL10, PMAIP1, IL1B, GNA15, and CD14) were screened from ARGs by machine learning. A total of 102 miRNAs, 13 TFs and 23 therapeutic drugs were predicted targeting these crucial genes. The clinical prediction model of the crucial genes has shown good predictive capability. The Mendelian randomization analysis demonstrated that apoptosis is a risk factor for AMI. Lastly, the expression of CDKN1A, CD14 and IL1B was verified in the AMI mouse model and external dataset. In this study, ARGs were screened by machine learning algorithms, and verified by qRT-PCR in the AMI mouse model. Finally, we demonstrated that CDKN1A, CD14 and IL1B were the crucial genes involved in apoptosis in AMI. These genes may provide new target for the recognition and intervention of apoptosis in AMI.

Zhu H ，Li M ，Wu J ，Yan L ，Xiong W ，Hu X ，Lu Z ，Li C ，Cai H ... -  《PeerJ》

Comparison of Two Modern Survival Prediction Tools, SORG-MLA and METSSS, in Patients With Symptomatic Long-bone Metastases Who Underwent Local Treatment With Surgery Followed by Radiotherapy and With Radiotherapy Alone.

Survival estimation for patients with symptomatic skeletal metastases ideally should be made before a type of local treatment has already been determined. Currently available survival prediction tools, however, were generated using data from patients treated either operatively or with local radiation alone, raising concerns about whether they would generalize well to all patients presenting for assessment. The Skeletal Oncology Research Group machine-learning algorithm (SORG-MLA), trained with institution-based data of surgically treated patients, and the Metastases location, Elderly, Tumor primary, Sex, Sickness/comorbidity, and Site of radiotherapy model (METSSS), trained with registry-based data of patients treated with radiotherapy alone, are two of the most recently developed survival prediction models, but they have not been tested on patients whose local treatment strategy is not yet decided. (1) Which of these two survival prediction models performed better in a mixed cohort made up both of patients who received local treatment with surgery followed by radiotherapy and who had radiation alone for symptomatic bone metastases? (2) Which model performed better among patients whose local treatment consisted of only palliative radiotherapy? (3) Are laboratory values used by SORG-MLA, which are not included in METSSS, independently associated with survival after controlling for predictions made by METSSS? Between 2010 and 2018, we provided local treatment for 2113 adult patients with skeletal metastases in the extremities at an urban tertiary referral academic medical center using one of two strategies: (1) surgery followed by postoperative radiotherapy or (2) palliative radiotherapy alone. Every patient's survivorship status was ascertained either by their medical records or the national death registry from the Taiwanese National Health Insurance Administration. After applying a priori designated exclusion criteria, 91% (1920) were analyzed here. Among them, 48% (920) of the patients were female, and the median (IQR) age was 62 years (53 to 70 years). Lung was the most common primary tumor site (41% [782]), and 59% (1128) of patients had other skeletal metastases in addition to the treated lesion(s). In general, the indications for surgery were the presence of a complete pathologic fracture or an impending pathologic fracture, defined as having a Mirels score of ≥ 9, in patients with an American Society of Anesthesiologists (ASA) classification of less than or equal to IV and who were considered fit for surgery. The indications for radiotherapy were relief of pain, local tumor control, prevention of skeletal-related events, and any combination of the above. In all, 84% (1610) of the patients received palliative radiotherapy alone as local treatment for the target lesion(s), and 16% (310) underwent surgery followed by postoperative radiotherapy. Neither METSSS nor SORG-MLA was used at the point of care to aid clinical decision-making during the treatment period. Survival was retrospectively estimated by these two models to test their potential for providing survival probabilities. We first compared SORG to METSSS in the entire population. Then, we repeated the comparison in patients who received local treatment with palliative radiation alone. We assessed model performance by area under the receiver operating characteristic curve (AUROC), calibration analysis, Brier score, and decision curve analysis (DCA). The AUROC measures discrimination, which is the ability to distinguish patients with the event of interest (such as death at a particular time point) from those without. AUROC typically ranges from 0.5 to 1.0, with 0.5 indicating random guessing and 1.0 a perfect prediction, and in general, an AUROC of ≥ 0.7 indicates adequate discrimination for clinical use. Calibration refers to the agreement between the predicted outcomes (in this case, survival probabilities) and the actual outcomes, with a perfect calibration curve having an intercept of 0 and a slope of 1. A positive intercept indicates that the actual survival is generally underestimated by the prediction model, and a negative intercept suggests the opposite (overestimation). When comparing models, an intercept closer to 0 typically indicates better calibration. Calibration can also be summarized as log(O:E), the logarithm scale of the ratio of observed (O) to expected (E) survivors. A log(O:E) > 0 signals an underestimation (the observed survival is greater than the predicted survival); and a log(O:E) < 0 indicates the opposite (the observed survival is lower than the predicted survival). A model with a log(O:E) closer to 0 is generally considered better calibrated. The Brier score is the mean squared difference between the model predictions and the observed outcomes, and it ranges from 0 (best prediction) to 1 (worst prediction). The Brier score captures both discrimination and calibration, and it is considered a measure of overall model performance. In Brier score analysis, the "null model" assigns a predicted probability equal to the prevalence of the outcome and represents a model that adds no new information. A prediction model should achieve a Brier score at least lower than the null-model Brier score to be considered as useful. The DCA was developed as a method to determine whether using a model to inform treatment decisions would do more good than harm. It plots the net benefit of making decisions based on the model's predictions across all possible risk thresholds (or cost-to-benefit ratios) in relation to the two default strategies of treating all or no patients. The care provider can decide on an acceptable risk threshold for the proposed treatment in an individual and assess the corresponding net benefit to determine whether consulting with the model is superior to adopting the default strategies. Finally, we examined whether laboratory data, which were not included in the METSSS model, would have been independently associated with survival after controlling for the METSSS model's predictions by using the multivariable logistic and Cox proportional hazards regression analyses. Between the two models, only SORG-MLA achieved adequate discrimination (an AUROC of > 0.7) in the entire cohort (of patients treated operatively or with radiation alone) and in the subgroup of patients treated with palliative radiotherapy alone. SORG-MLA outperformed METSSS by a wide margin on discrimination, calibration, and Brier score analyses in not only the entire cohort but also the subgroup of patients whose local treatment consisted of radiotherapy alone. In both the entire cohort and the subgroup, DCA demonstrated that SORG-MLA provided more net benefit compared with the two default strategies (of treating all or no patients) and compared with METSSS when risk thresholds ranged from 0.2 to 0.9 at both 90 days and 1 year, indicating that using SORG-MLA as a decision-making aid was beneficial when a patient's individualized risk threshold for opting for treatment was 0.2 to 0.9. Higher albumin, lower alkaline phosphatase, lower calcium, higher hemoglobin, lower international normalized ratio, higher lymphocytes, lower neutrophils, lower neutrophil-to-lymphocyte ratio, lower platelet-to-lymphocyte ratio, higher sodium, and lower white blood cells were independently associated with better 1-year and overall survival after adjusting for the predictions made by METSSS. Based on these discoveries, clinicians might choose to consult SORG-MLA instead of METSSS for survival estimation in patients with long-bone metastases presenting for evaluation of local treatment. Basing a treatment decision on the predictions of SORG-MLA could be beneficial when a patient's individualized risk threshold for opting to undergo a particular treatment strategy ranged from 0.2 to 0.9. Future studies might investigate relevant laboratory items when constructing or refining a survival estimation model because these data demonstrated prognostic value independent of the predictions of the METSSS model, and future studies might also seek to keep these models up to date using data from diverse, contemporary patients undergoing both modern operative and nonoperative treatments. Level III, diagnostic study.

Lee CC ，Chen CW ，Yen HK ，Lin YP ，Lai CY ，Wang JL ，Groot OQ ，Janssen SJ ，Schwab JH ，Hsu FM ，Lin WH ... -  《-》